Motor imagery is a core paradigm in brain–computer interface (BCI) research. Despite notable progress, the accuracy of electroencephalography (EEG) decoding remains constrained by pronounced intersubject physiological variability. Domain generalization (DG) methods offer a feasible solution as they do not require target subject data during training. However, existing DG approaches are limited by insufficient modeling of temporal dependencies, inadequate exploitation of feature diversity, and overly simplistic training strategies. To address these issues, we propose a novel temporal generation (TGen) component that integrates a temporal convolutional network with a variational autoencoder to capture temporal dependencies in EEG signals. It employs a dual-branch design combining random convolutions with covariance regularization to enhance feature diversity. Building upon TGen, we further construct the DG model, named DG-MTLNet, by incorporating cross electrode convolution and multitask learning. Evaluations on the public BCI competition IV datasets 2a and 2b, the large-scale public datasets OpenBMI and EDSP, and the diverse dataset MI-GS, demonstrate that DG-MTLNet outperforms the best baseline models, achieving mean accuracy improvements of 2.50%, 3.11%, 3.23%, 1.54%, and 3.47%, respectively.

Accurate motor imagery (MI) classification in EEG-based brain-computer interfaces (BCIs) is essential for applications in engineering, medicine, and artificial intelligence. Due to the limitations of single-model approaches, hybrid model architectures have emerged as a promising direction. In particular, convolutional neural networks (CNNs) and vision transformers (ViTs) demonstrate strong complementary capabilities, leading to enhanced performance. This study proposes a series of novel models, termed as CNNViT-MI, to explore the synergy of CNNs and ViTs for MI classification. Specifically, five fusion strategies were defined: parallel integration, sequential integration, hierarchical integration, early fusion, and late fusion. Based on these strategies, eight candidate models were developed. Experiments were conducted on four datasets: BCI competition IV dataset 2a, BCI competition IV dataset 2b, high gamma dataset, and a self-collected MI-GS dataset. The results demonstrate that CNNViT-MILF-a achieves the best performance among all candidates by leveraging ViT as the backbone for global feature extraction and incorporating CNN-based local representations through a late fusion strategy. Compared to the best-performing state-of-the-art (SOTA) methods, mean accuracy was improved by 2.27%, 2.31%, 0.74%, and 2.50% on the respective datasets, confirming the model's effectiveness and broad applicability, other metrics showed similar improvements. In addition, significance analysis, ablation studies, and visualization analysis were conducted, and corresponding clinical integration and rehabilitation protocols were developed to support practical use in healthcare.

Only a few key fish individuals can play a dominant role in actual fish group, therefore, it is reasonable to infer group activities from the relationship between individual actions. However, the complex underwater environment, rapid and similar fish individual movements are likely to cause the indistinct action characteristics, as well as adhesion of data distribution, and it is difficult to infer the relationship between individual actions directly by using graph convolutional network (GCN). Therefore, this article proposes a graph convolution vector calibration (GCVC) network for fish group activity recognition through individual action relationship reasoning. By improving reasoning ability of GCN, an activity feature vector calibration module is designed to solve the data adhesion and mismatch between the estimated and true distribution. The idea is to first count the distribution of the original data, and make each dimension of its active feature vector follow the Gaussian distribution, so as to generate a better similar category distribution. In addition, we also produced a fish activity dataset to verify the performance of the proposed algorithm. The experimental results show that the GCVC achieves a group activity recognition accuracy of 93.33%, and the Macro-F1 is 93.25%, which is 19.21% and 24.2% higher than before, respectively. By using GCVC, the corrected activity feature vector distribution is more consistent, and the data adhesion is reduced, the model can achieve more fully supervised learning.

The automatic detection and identification of fish from underwater videos is of great significance for fishery resource assessment and ecological environment monitoring. However, due to the poor quality of underwater images and unconstrained fish movement, traditional hand-designed feature extraction methods or convolutional neural network (CNN)-based object detection algorithms cannot meet the detection requirements in real underwater scenes. Therefore, to realize fish recognition and localization in a complex underwater environment, this paper proposes a novel composite fish detection framework based on a composite backbone and an enhanced path aggregation network called Composited FishNet. By improving the residual network (ResNet), a new composite backbone network (CBresnet) is designed to learn the scene change information (source domain style), which is caused by the differences in the image brightness, fish orientation, seabed structure, aquatic plant movement, fish species shape and texture differences. Thus, the interference of underwater environmental information on the object characteristics is reduced, and the output of the main network to the object information is strengthened. In addition, to better integrate the high and low feature information output from CBresnet, the enhanced path aggregation network (EPANet) is also designed to solve the insufficient utilization of semantic information caused by linear upsampling. The experimental results show that the average precision (AP)0.5:0.95, AP50and average recall (AR)max=10of the proposed Composited FishNet are 75.2%, 92.8% and 81.1%, respectively. The composite backbone network enhances the characteristic information output of the detected object and improves the utilization of characteristic information. This method can be used for fish detection and identification in complex underwater environments such as oceans and aquaculture.

Model-driven Software Development (MDSD) approaches struggle when modeling context-dependent and dynamic systems, as their underlying metamodels cannot capture context-dependent concepts and relations. By contrast, role-based modeling has been studied for more than 35 years as a promising paradigm to model context-dependent and dynamic systems. Although some approaches have considered the application of roles on the metamodel level, no approach employed a contextual and relational role-based metamodel as the basis of a modeling framework. To remedy this, we employ the Compartment Role Object Model (CROM) which is a contextual and relational role-based modeling language, as the underlying metamodel of a novel Role-based Modeling Framework (RMF). In particular, our framework is able to generate inter-operable Java source code that permits the programmatic creation, manipulation, and persistence of role-based models. We illustrate the applicability of RMF by modeling a small system with context-dependent concepts and relations, generating corresponding Java source code, and employing it to load, manipulate, and store role-based models.